An ASP Approach for Reasoning on Neural Networks under a Finitely Many-Valued Semantics for Weighted Conditional Knowledge Bases

作     者：GIORDANO, L. A. U. R. A. THESEIDER DUPRE, D. A. N. I. E. L. E. 

作者机构：Univ Piemonte Orientale DISIT Vercelli Italy 

出 版 物：《THEORY AND PRACTICE OF LOGIC PROGRAMMING》 (逻辑程序设计理论与实践)

年 卷 期：2022年第22卷第4期

页      面：589-605页

核心收录：

学科分类：08[工学] 0835[工学-软件工程] 0701[理学-数学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：INDAM-GNCS Project 2020 

主　　题：description logics neural networks multi-valued logics answer set programming 

摘      要：Weighted knowledge bases for description logics with typicality have been recently considered under a concept-wise multipreference semantics (in both the two-valued and fuzzy case), as the basis of a logical semantics of multilayer perceptrons (MLPs). In this paper we consider weighted conditional ALC knowledge bases with typicality in the finitely many-valued case, through three different semantic constructions. For the boolean fragment LC of ALC we exploit answer set programming and asprin for reasoning with the concept-wise multipreference entailment under a phi-coherent semantics, suitable to characterize the stationary states of MLPs. As a proof of concept, we experiment the proposed approach for checking properties of trained MLPs.